Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references and citations related to bibliographies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rin
    -0.17
    edException
    -0.15
    arde
    -0.14
    å½¹
    -0.14
    ello
    -0.14
     tails
    -0.14
    apan
    -0.14
    rank
    -0.14
    la
    -0.13
    466
    -0.13
    POSITIVE LOGITS
    lical
    0.21
    lio
    0.18
    TeX
    0.17
    etch
    0.16
    woke
    0.16
    asset
    0.15
    íĩ´
    0.15
    utow
    0.15
    avanaugh
    0.15
     sorts
    0.14
    Act Density 0.011%

    No Known Activations